LLM EXPLORER
 LLM Explorer: A Curated Large Language Model Directory and Analytics
Dark Theme
  LLM  List    LLM Hosting    LLM Leaderboards    Blog    Newsfeed    Advertise

Jais Family 13B by inceptionai

 »  All LLMs  »  inceptionai  »  Jais Family 13B   URL Share it on

  236   
  Arxiv:2307.09288   Arxiv:2308.16149   Arxiv:2402.12840   Ar   Arabic   Custom code   Decoder   En   English   Jais   Jais-family   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/inceptionai/jais-family-13b 

Jais Family 13B Benchmarks

LLME Score: 0.2192
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Jais Family 13B (inceptionai/jais-family-13b)

Jais Family 13B Parameters and Internals

Model Type 
Decoder, Causal LM
Use Cases 
Areas:
Research, Commercial Use, Natural Language Understanding, Text Generation
Applications:
Chat assistants for Arabic speakers, Sentiment analysis, Bilingual document summarization
Primary Use Cases:
Chat applications, Arabic cultural and linguistic analyses, Mechanistic interpretability analyses
Limitations:
Not suitable for use in non-Arabic or non-English languages without further adaptation
Considerations:
Language-specific capabilities, cultural context alignment.
Additional Notes 
Jais models provide better cultural understanding than English-centric models.
Supported Languages 
Arabic (MSA), English (Proficient)
Training Details 
Data Sources:
Web, Code, Books, Scientific, Synthetic
Data Volume:
1.6 Trillion tokens
Methodology:
Pre-trained from scratch or adaptively from Llama-2
Context Length:
16384
Hardware Used:
Condor Galaxy (CG) supercomputer platform with 64 Cerebras CS-2 Wafer-Scale Engines
Model Architecture:
Auto-regressive, transformer-based, decoder-only (GPT-3, SwiGLU non-linear activation, ALiBi position encoding)
Responsible Ai Considerations 
Mitigation Strategies:
Bias reduction techniques used, but model may still exhibit biases.
Input Output 
Input Format:
Text
Accepted Modalities:
text
Output Format:
Generates text
Performance Tips:
Model supports large context lengths up to 16k tokens for certain configurations.
Release Notes 
Date:
2023
Notes:
Release included 20 models trained on up to 1.6 trillion tokens across 8 sizes.
LLM NameJais Family 13B
Repository 🤗https://huggingface.co/inceptionai/jais-family-13b 
Model Size13b
Required VRAM53.9 GB
Updated2024-11-04
Maintainerinceptionai
Model Typejais
Model Files  10.0 GB: 1-of-6   9.8 GB: 2-of-6   10.0 GB: 3-of-6   9.8 GB: 4-of-6   9.8 GB: 5-of-6   4.5 GB: 6-of-6
Supported Languagesar en
Gated ModelYes
Model ArchitectureJAISLMHeadModel
Licenseproprietary
Model Max Length2048
Transformers Version4.40.1
Tokenizer ClassPreTrainedTokenizerFast
Padding Token<|endoftext|>
Vocabulary Size84992
Torch Data Typefloat32
Activation Functionswiglu

Best Alternatives to Jais Family 13B

Best Alternatives
Context / RAM
Downloads
Likes
Jais Family 13B Chat0K / 53.9 GB45419
Jais 13B Chat0K / 53.9 GB17557134
Jais 13B0K / 53.9 GB8487138
Jais 13B Chat0K / 53.9 GB2061140
Jais 13B0K / 53.9 GB1401143
Note: green Score (e.g. "73.2") means that the model is better than inceptionai/jais-family-13b.

Rank the Jais Family 13B Capabilities

🆘 Have you tried this model? Rate its performance. This feedback would greatly assist ML community in identifying the most suitable model for their needs. Your contribution really does make a difference! 🌟

Instruction Following and Task Automation  
Factuality and Completeness of Knowledge  
Censorship and Alignment  
Data Analysis and Insight Generation  
Text Generation  
Text Summarization and Feature Extraction  
Code Generation  
Multi-Language Support and Translation  

What open-source LLMs or SLMs are you in search of? 42577 in total.

Email us: info@extractum.io. Our Privacy Policy  | Terms and Conditions  | Suggest an improvement.
Our Social Media →  
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241227
  Support LLM Explorer